The FORECAST Procedure
- Overview
-
Getting Started
Giving Dates to Forecast ValuesComputing Confidence LimitsForm of the OUT= Data SetPlotting ForecastsPlotting ResidualsModel Parameters and Goodness-of-Fit StatisticsControlling the Forecasting MethodIntroduction to Forecasting MethodsTime Trend ModelsTime Series MethodsCombining Time Trend with Autoregressive Models -
Syntax
-
Details
-
Examples
- References
Data Periodicity and Time Intervals
The INTERVAL= option is used to establish the frequency of the time series. For example, INTERVAL=MONTH specifies that each observation in the input data set represents one month. If INTERVAL=MONTH2, each observation represents two months. Thus, there is a two-month time interval between each pair of successive observations, and the data frequency is bimonthly.
See Chapter 4: Date Intervals, Formats, and Functions, for details about the interval values supported.
The INTERVAL= option is used together with the ID statement to fully describe the observations that make up the time series. The first variable specified in the ID statement is used to identify the observations. Usually, SAS date or datetime values are used for this variable. PROC FORECAST uses the ID variable in the following ways:
-
to validate the data periodicity. When the INTERVAL= option is specified, the ID variable is used to check the data and verify that successive observations have valid ID values that correspond to successive time intervals. When the INTERVAL= option is not used, PROC FORECAST verifies that the ID values are nonmissing and in ascending order. A warning message is printed when an invalid ID value is found in the input data set.
-
to check for gaps in the input observations. For example, if INTERVAL=MONTH and an input observation for January 1970 is followed by an observation for April 1970, there is a gap in the input data, with two observations omitted. When a gap in the input data is found, a warning message is printed, and PROC FORECAST processes missing values for each omitted input observation.
-
to label the forecast observations in the output data set. The values of the ID variable for the forecast observations after the end of the input data set are extrapolated according to the frequency specifications of the INTERVAL= option. If the INTERVAL= option is not specified, the ID variable is extrapolated by incrementing the ID variable value for the last observation in the input data set by the INTPER= value, if specified, or by one.
The ALIGN= option controls the alignment of SAS dates. See Chapter 4: Date Intervals, Formats, and Functions, for more information.